Monday, February 27, 2006

Experimental economics is going commercial

A mainstay empirical method in economics is "econometrics", which has been called a "nonexperimental" method of investigating causal relations. The usual argument is that the economic system is not subject to experimentation; nonexperimental data will have to be subject to different methods of analysis. (The contrast of course is with the natural sciences, where experimentation is standard.)

Increasingly though economics adopting experimental techniques. The latest Scientific American reports on the work of Kay-Yut Chen at Hewlett-Packard. The difference is that direct commercial applications are being explored:

Chen thinks he has solved the sandbagging problem: have each salesperson choose a personal balance of fixed and variable compensation. For example, the salesperson can choose a high commission percentage with no fixed salary or, at the other extreme, a modest fixed salary and no commission--or some combination in between. Each choice implicitly reveals how much the salesperson plans to sell, much as an insurance subscriber's choice of deductible and premium reveals how sick she is. Based on a truth-telling mechanism from game theory, this design works on paper. But as an experimental economist, Chen will keep testing it empirically, comparing the emerging design with other available models, such as the one he is testing today.

Chen has successfully used that approach to help HP managers design good contracts with retailers and resellers, and he is starting to tackle other thorny problems for his employer: figuring out how to protect HP's bottom line against international currency fluctuations and discovering ways for brick-and-mortar retailers and HP's online store to coexist happily.

Econometrics is nowhere near being supplanted by experimental economics, even in the long run. But I'd be glad to see experimentation becoming a fairly common research method in the field in the medium term.


Amadeo said...

As a tool of Economics, econometrics has of late been in the cross-hairs of some Economics pundits here in the US blogosphere.

The issue apparently is not so much that it is not a science but simply a tool (Economics is the science), but more that some users of it are selling their results as inassailable science and thus should not be questioned.

Econblogger said...

Econometrics is very much assailable.

As with GMA-issue though, the best reply is: Show me the alternative.

Michael Parente said...

I've always wondered why "commercial research" is so often viewed as unscientific. The important standard for science should be the replicability of the results not the purpose of the research.